Abstract: A diagnosis supporting system according to embodiments includes a memory that stores medical information including patient information relating to a condition of a patient, and intervention information relating to an intervention for the patient; and processing circuitry that extracts a change point in the medical information, that calculates a first change amount indicating a change in the patient information between before and after the change point, and a second change amount indicating a change in the intervention information between before and after the change point, and that performs display based on the first change amount and the second change amount in a display mode set according to at least one of the first change amount and the second change amount.

Abstract: Certain embodiments are directed to systems and methods for automatically providing data indicative of one or more characteristics of services that may be recommended to a particular patient, wherein the services are executable at least in part electronically based on data generated and provided by a system for facilitating access to the services. The generated data may be utilized for generating one or more user interfaces providing data regarding derived standard pricing data that is automatically assigned to the referred services and which may be attributable to a patient based at least in part on the patient's usage of the services.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a clinical recommendation for medical treatment of a patient.

Abstract: Computer program products, methods, systems, apparatus, and computing entities are described for identifying significant incidental findings from medical records. In one example embodiment, an example computing device receives a medical report and derives a textual component from the medical report. The computing device then identifies one or more medical findings from the textual component and determines a clinical context for each of the one or more medical findings. The computing device then identifies one or more clinical cues from the one or more medical findings and generates one or more condition signals from the one or more clinical cues. The computing device then generates a condition alert from the one or more condition signals. The condition alert is indicative of a significant incidental finding. Using various embodiments contemplated herein, significant incidental findings can be identified for follow-up by a user.

Abstract: Provided are systems, methods, and devices for sleep intervention quality assessment. Methods include receiving measurement data from a plurality of data sources, the measurement data comprising a plurality of measurements of biological parameters of a user before and after a sleep intervention, and receiving treatment data comprising one or more treatment parameters associated with the sleep intervention. Methods further include generating, using one or more processors, a plurality of quality assessment metrics based on the received measurement data, the plurality of quality assessment metrics being generated based, at least in part, on a comparison of the plurality of measurements of biological parameters before and after the sleep intervention, and generating a report based, at least in part, on the plurality of quality assessment metrics.

Abstract: A clinical event outcome scoring system and method are used to determine a Severity of Illness Clinical Key (SICK) score, which is a probable degree of successful outcome for a patient about to undergo a specific clinical event, such as for example, coronary bypass surgery, hip replacement, bariatric surgery, discharge from a hospital for home recovery, a course of chemotherapy, radiation, or other treatment protocol. The system and method analyzes historical patient data to generate a statistical model for each specific clinical event of interest, which can then be used to determine a SICK score for a patient about to undergo the same clinical event. In some embodiments, the statistical model can be “fine-tuned” to render subcategories of statistical models tailored for certain patient populations about to undergo the same clinical event.

Abstract: A computer-implemented method includes selecting a group of sets. Each set has values for immutable attributes that match values for at least one mutable attribute in a prediction request. The method includes determining a conditional covariance matrix for the group of sets. The method includes generating a deviation model based on the conditional covariance matrix. The method includes sampling the deviation model to generate multiple sets of likely mutable attribute values. The method includes automatically selecting a neural network from a set of outcome models based on the likely mutable attribute values. Each neural network includes a set of layers. Each layer includes a set of nodes. A first layer receives inputs at the set of nodes of the input layer. Each layer other than the first layer receives outputs from a preceding layer and creates modified outputs. A last layer outputs the modified outputs from the neural network.

Abstract: Embodiments herein include a method for detecting a health condition of a subject. The method can include obtaining a biological sample from the subject and placing it into a container having a headspace surrounding the biological sample. The method can include contacting a gas from the headspace with a chemical sensor element, the chemical sensor element including one or more discrete graphene varactors. The method can include sensing and storing capacitance of the discrete graphene varactors to obtain a sample data set. Other embodiments are also included herein.

Abstract: A respiratory disease analytics system provides respiratory disease risk reports to a patient, provider, or third-party entity describing a patient's risk of experiencing a medication usage event given data in a geographic region. Regional data, including air pollutant conditions, weather conditions, demographic information, built environment factors, and regional health conditions for a geographic region are accessed from other sources and assigned based on event data recorded during a medicament usage event, as collected by sensors associated with the patient's medicament device/s. The regional data is assigned to medicament usage events occurring within a period of time. The assigned regional data is analyzed to determine an expected number of medication usage events for the geographic region occurring over the period of time.

Abstract: Methods and devices include identifying a plurality of target users for the digital therapeutic based on one or more target parameters, conducting outreach to one or more of the plurality of target users using an outreach medium, identifying an activation mechanism to optimize use of the digital therapeutic, and encouraging an engagement level of the digital therapeutic by one or more of the plurality of target users.

Abstract: Data that is derived from a medical device connected to or communicating with, a patient monitor mount, is detected by the patient monitor mount. The data is monitored for events associated with the medical device. The patient monitor mount then determines that the monitored event corresponds to an event. The patient monitor mount generates at least one command for a visualization device to change the data displayed on the visualization device. The command is then transmitted to the visualization device. Related apparatus, systems, methods and articles are also described.

Abstract: A suite of fluidless predictive machine learning models includes a fluidless mortality module, smoking propensity model, and prescription fills model. The fluidless machine learning models are trained against a corpus of historical underwriting applications of a sponsoring enterprise, including clinical data of historical applicants. Fluidless models are trained by application of a random forest ensemble including survival, regression, and classification models. The trained models produce high-resolution, individual mortality scores. A fluidless underwriting protocol runs these predictive models to assess mortality risk and other risk attributes of a fluidless application that excludes clinical data to determine whether to present an accelerated underwriting offer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for using machine learning to generate precision predictions of readiness. In some implementations, a database is accessed to obtain status data that indicates activities or attributes of a subject. A set of feature scores is derived from the status data for the subject, the set of feature scores including values indicative of attributes or activities of the subject. The set of feature scores to one or more models that have been configured to predict readiness of subjects to satisfy one or more readiness criteria. The one or models can be models configured using machine learning training. Based on processing performed using the one or more machine learning models and the set of feature scores, a prediction regarding the subject's ability to achieve readiness to satisfy the one or more readiness criteria is generated.

Abstract: A method for estimating a likelihood of a stroke condition of a subject, the method comprising: acquiring clinical measurement data pertaining to said subject, said clinical measurement data including at least one of image data, sound data, movement data, and tactile data; extracting from said clinical measurement data, potential stroke features according to at least one predetermined stroke assessment criterion; comparing said potential stroke features with classified sampled data acquired from a plurality of subjects, each positively diagnosed with at least one stroke condition, defining a positive stroke dataset; and determining, according to said comparing, a probability of a type of said stroke condition, and a probability of a corresponding stroke location of said stroke condition with respect to a brain location of said subject.

Abstract: A system and method for generating a metabolic dysfunction nourishment program comprises a computing device configured to obtain a metabolic component as a function of a user metabolic system, identify a metabolic panel as a function of the metabolic component, wherein identifying further comprises receiving a status grading, ascertaining a metabolic functional goal, and identifying the metabolic panel as a function of the status grading, metabolic functional goal, and metabolic component using a metabolic machine-learning model, determine an edible as a function of the metabolic panel, wherein determining further comprises receiving a nourishment composition from an edible directory, producing a nourishment demand as a function of the metabolic panel, and determining the edible as a function of the nourishment composition and nourishment demand using an edible machine-learning model, and generate a nourishment program as a function of the edible and a metabolic outcome using a nourishment machine-learning mo

Abstract: Techniques are described herein for drawing conclusions using free form texts and external resources. In various embodiments, free form input data (202) may be segmented (504) into a plurality of input data segments. A first input data segment may be compared (510) with an external resource (304) to identify a first candidate conclusion. A reinforcement learning trained agent (310) may be applied (512) to make a first determination of whether to accept or reject the first candidate conclusion. Similar actions may be performed with a second input data segment to make a second determination of whether to accept or reject a second candidate conclusion. A final conclusion may be presented (522) based on the first and second determinations of the reinforcement learning trained agent with respect to at least the first candidate conclusion and the second candidate conclusion.

Abstract: A computer-implemented method and corresponding output generator for handling alarm events, generated by a subject/patient monitoring device, and generating clinician-perceptible outputs indicative of the alarm events. Alarm events are divided into non-actionable and actionable alarm events. Information on non-actionable alarm events is stored. Stored information on non-actionable alarm events is contained in a clinician-perceptible output generated in response to detecting an actionable alarm event.

Abstract: A system (100) includes an end point prediction engine (150) that predicts an end point (302) using a machine learning model (132) and one or more clinical report objects (152) for a patient, wherein the machine learning model inputs the one or more clinical report objects and outputs the predicted end point according to phrases or n-grams in the one or more clinical report objects. An end point visualization interface (160) visualizes the predicted end point (302) using a scorecard (162) or a timeline (164). An end point modeling engine (130) generates the machine learning model from training data that includes validated end points (122) and clinical report objects (116).

Abstract: Systems, devices, and techniques are disclosed for administering and tracking medicine to patients and providing health management capabilities for patients and caregivers. In some aspects, a system includes an injection pen device in communication with a mobile communication device having a software application to determine a recommended dose based on prior dose data, analyte data, and nutrient data and to generate a report illustrative of a relationship between the medicine data, the health data, and the contextual data.

Abstract: A physiological monitoring device includes: a sensor interface, a display configured to display information related to the patient, and at least one processor. The at least one processor is configured to: operate the physiological monitoring device into a non-transport mode while docked to one of at least one monitor mount; display first location context information corresponding to a first patient care area on the display while the physiological monitoring device is operating in the non-transport mode in the first patient care area; detect an undocking event in response to undocking the physiological monitoring device from a first monitor mount of the at least one monitor mount, wherein the first monitor mount is located in the first patient care area; and in response to detecting the undocking event, operate the physiological monitoring device in a transport mode, including changing the first location context information to transport context information on the display.