Abstract: A system is provided for encoding genomics data for secure storage and processing. In particular, the system may comprise a client and server operating environment that uses a unique encoding algorithm to transform genomics data and/or metadata to produce encoded genomics data and/or metadata. In some embodiments, the encoded genomics data and/or metadata may be encrypted using one or more encryption algorithms. The encoded and/or encrypted genomics data may be stored on a secure server (e.g., a cloud environment) that may perform subsequent processing steps on the encoded and/or encrypted genomics data. Once the processing steps have been completed, the server may transmit one or more outputs associated with the genomics data and/or metadata to a client device. In this way, the system provides an efficient and secure way to store and process genomics data.

Abstract: A system is provided for generating machine learning-based associations for electronic data records. In particular, the system may access one or more relevant databases and use machine learning algorithms to automatically generate associations between certain concepts based on the contents and/or hierarchical structures of such databases. The system may further intelligently calculate weight values for each of the associations that may represent the strength of the relatedness or relevance between concepts. Once the associations are generated, the system may, in response to a query for information related to a certain concept, generate and provide a context-relevant view of the concept to the user. In this way, the system provides an efficient way to correlate information within electronic data records.

Abstract: Provided are a method and system for automatically managing clinical trial image evaluation data. The method automatically managing clinical trial image evaluation data comprises the operations of: obtaining first image evaluation data and second image evaluation data from a first evaluator and a second evaluator, respectively; analyzing the obtained image evaluation data by evaluation items, whether the obtained image evaluation data conforms to preset evaluation rules; in a case in which the obtained image evaluation data includes an evaluation item which does not conform to the evaluation rules, automatically providing a query including a correction request and help with respect to the evaluation item that does not conform to the evaluation rules; and determining whether the first image evaluation data and the second image evaluation data match each other with respect to the evaluation items.

Abstract: Described herein are systems, methods, and apparatus for electronically drawing and editing representations of chemical structures using an intuitive user interface. This user interface, the context-aware virtual keyboard, makes it faster and easier to draw and edit chemical structure representations by guiding the user through the sequence of steps required to produce the representation in a context-based, non-linear fashion. The context-based virtual keyboard allows a user to quickly create graphical representations of complex chemical structures by using the structure itself as a basis for presenting efficient options for subsequent drawing/editing steps. Different possible and/or likely actions (e.g., edits to a chemical structure being drawn) are presented to the user based on a selected navigation position on the drawing.

Abstract: Systems, methods, and apparatus are provided that allow a user to draw and edit a chemical structure using one or more gestures performed on an input interface. For example, the user may assign an atom label to a chemical structure representation by performing a press and tap gesture, change a chemical bond characteristic in the chemical structure representation by performing a tap gesture, and/or lengthen a molecular chain in the chemical structure representation by performing a drag gesture. The user may also rotate the chemical structure representation in the graphical display by performing one or more rotation gestures.

Abstract: Methods, systems, computer-readable media, and apparatuses for determining a sedentary state of a user are disclosed. The apparatuses can be fastened to the user and include sensors configured to detect movement of the user. The apparatuses can also include a circuit coupled to the sensors. The circuits may be configured to determine, using the sensors, whether the user is sedentary; and in response to determining that the user is sedentary, determine one or more physiological attributes of the user of the device.

Abstract: Methods and systems for generating episodes of activity, such as episodes of care. One method includes generating, by a processor, a graphical user interface for display to a user. The method also includes receiving, by a processor, (1) a first selection of a trigger event for an episode of care from the user through the graphical user interface, (2) a second selection of at least one time period for the episode of care from the user through the graphical user interface, and (3) a third selection of at least one claim category for the episode of care from the user through the graphical user interface. The method further includes creating, by the processor, parameters for the episode of care based on the first, second, and third selections, wherein the parameters are applied to a plurality of medical claims to group at least two of the plurality of medical claims.

Abstract: A system is provided for encoding genomics data for secure storage and processing. In particular, the system may comprise a client and server operating environment that uses a unique encoding algorithm to transform genomics data and/or metadata to produce encoded genomics data and/or metadata. In some embodiments, the encoded genomics data and/or metadata may be encrypted using one or more encryption algorithms. The encoded and/or encrypted genomics data may be stored on a secure server (e.g., a cloud environment) that may perform subsequent processing steps on the encoded and/or encrypted genomics data. Once the processing steps have been completed, the server may transmit one or more outputs associated with the genomics data and/or metadata to a client device. In this way, the system provides an efficient and secure way to store and process genomics data.

Abstract: Various embodiments enable calibrating a non-invasive blood pressure measurement device by determining multiple parameters defining a stress-strain relationship of an artery of a patient. The device may obtain output signals from a blood pressure sensor at two or more measurement elevations. The obtained measurement signals may be filtered into AC and quasi-DC components, and results fit to exponential functions to calculate an arterial time constant and a veinous time constant related to vein draining/filling rates. The arterial and veinous time constants may be used to calculate an infinity ratio. The infinity ratio and the obtained sensor output may be used to calculate values for multiple parameters defining a stress-strain relationship of a measured artery. Once defined, this stress-strain relationship may be stored and applied to future sensor output signals (e.g., blood pressure measuring sessions) to infer patient blood pressure.

Abstract: Described herein are systems and methods for indexing document data in order to facilitate chemical structure searching. The document data may include chemical structure data corresponding to a chemical structure. Bit-screening data and connection data in the chemical structure data may be identified. The bit-screening data may correspond to constituent elements of the chemical structure, and the connection data may correspond to connections between the one or more constituent elements. A string tag may be generated based on a portion of the identified bit-screening data. The string tag may include an alphanumeric value for describing the chemical structure that corresponds to the chemical structure data. The document data may be indexed based on the string tag. The chemical structure data corresponding to a chemical structure in the document may be searchable based on correlating at least a portion of text data of a query with the indexed document data.

Abstract: Methods of measuring a physical or physiological parameter using an integrated adhesive sensor array including a sensor hub and a detachable sensor pod are presented. In one example, a method comprises: establishing a first communication link between the sensor hub and a wireless receiver; attaching at least the sensor hub directly to a body; establishing a second communication link between the detachable sensor pod and the sensor hub; sensing a physical or physiological parameter by the detachable sensor pod; transmitting sensor data of the physical or physiological parameter from the detachable sensor pod to the sensor hub via the second communication link; and transmitting the sensor data from the sensor hub to the wireless receiver via the first communication link.

Abstract: Aspects discussed herein relate to employing deep learning to automate mapping and transformation of a source data set to a target data schema. A system may utilize deep learning algorithms to determine a mapping from the source schema to the target schema through identifying the source schema and creating a correspondence between source fields and target fields, and a corresponding data transformation. Artificial neural networks, configured as schema-level and instance-level classifiers, may generate a set of predictions based on the fields of the source data set and fields of the target data schema. These predictions may be combined with other predictions based on other criteria (such as similarity between the fields) to generate a complete prediction of a schema mapping. Similarly, deep learning techniques may be employed to determine an appropriate data transformation to transform source data content to an appropriate format for corresponding fields of the target schema.

Abstract: In certain embodiments, the invention relates to systems, methods, and apparatus that allow a user to visually augment a graphical rendering of either a chemical structure representation or a biological sequence representation with multi-dimensional information. A user captures a video image using a computing device such as a hand-held smart phone, computerized eye glasses or tablet computer. The video image includes information regarding at least one of a chemical structure and a biological sequence. A processor identifies, within the video image, a graphical representation of at least one of a chemical structure and a biological structure. The processor augments the graphical representation with additional information and provides the video data for presentation upon a display controlled by the computing device. The computing device presents the video data in substantially real time in relation to the capture of the video data by the computing device.

Abstract: Some methods may involve receiving, at a first node of the health network, encrypted sensor data from one or more sensors. The first node may be in a data communication path between the one or more sensors and other nodes of the health network. The method may involve decrypting, by the first node of the health network, only a portion of the encrypted sensor data, and transmitting the encrypted sensor data from the first node of the health network to a second node of the health network. The first node may be a gateway device. In some examples, the second node may be able to decrypt more of the encrypted sensor data than the first node.

Abstract: A device generates a capability map. The device receives one or more design spaces from a materials supplier, the one or more design spaces including candidate components and capabilities of tools available to the materials supplier. The device inputs a design space of the one or more design spaces into a machine learning model, the training data including a plurality of components including input materials and/or chemicals, and, for respective combinations of the plurality of components, a plurality of respective performance properties. The device receives as output from the model a capability map of the materials supplier storing possible combinations of performance properties and a respective difficulty of developing a composition with that combination of performance properties. The device outputs a user interface for display to a user indicating data of the capability map.

Abstract: A system and a method are disclosed that, in an embodiment, receive first input from a user of a candidate formulation recipe, and second input from the user of target properties and target property constraints. The system inputs the first input into a machine learning model, the model having been trained using historical training data, each element of the historical training data corresponding to a known formulation having a known feature representation, each known formulation having associated properties and statistical representations of each feature of the known formulation that form the known feature representation. The system receives as output from the model a predicted property of a candidate formulation derived using the first input and the likelihood that the candidate formulation satisfies the target property constraints using the second input. The system generates for display to the user a predicted likelihood that the predicted property satisfies the second input.

Abstract: A system to organize, search and display unstructured data comprising a token retrieval module, a document indexing engine, a subspace search module and a user interface module has been devised. The system retrieves a plurality of tokens and associates them with coordinates in subspace. It also retrieves documents and creates a multidimensional matrix of documents and tokens where each cell contains the number of times the token occurs in each document. That matrix is employed in a search using user specified search terms. The search results are displayed such that the search tokens occupy specific spatial coordinates and documents spatial coordinates are dictated by the relative preponderance of each search term in each document.

Abstract: Systems, methods, and apparatus are provided that allow a user to draw and edit a chemical structure using one or more gestures performed on an input interface, such as a touch pad or touch screen. For example, the user may assign an atom label to a chemical structure representation by performing a press and tap gesture, change a chemical bond characteristic in the chemical structure representation by performing a tap gesture, and/or lengthen a molecular chain in the chemical structure representation by performing a drag gesture. The user may also rotate the chemical structure representation in the graphical display by performing one or more rotation gestures.

Abstract: Disclosed are systems, devices, and methods for connecting a flexible circuit to a battery. Conductive pads are formed simultaneous with mounting and reflowing circuitry components on a flexible circuit, where the conductive pads serve as preformed tabs capable of being joined to terminals of a battery. The flexible circuit can be bent in a manner so that the conductive pads are positioned adjacent to the positive and negative terminals of a battery, such as a coin cell battery. The conductive pads can be attached to the terminals to form a cost-efficient and space-efficient design connecting the battery to the flexible circuit.

Abstract: A system and a method are disclosed for predicting design space quality for materials development and manufacture. In an embodiment, a processor receives input of a material property and a design space. The processor identifies a best data point. For each respective candidate material of the design space, the processor receives, as output from a model, a respective property value. The processor determines respective property values that exceed the property value of the best data point adds them to a subset of candidate materials. The processor determines a PFIC score for candidates in the subset. The processor generates a plurality of curves, each reflecting a respective probability distribution of property values. The processor determines a CMLI score based on the plurality of respective curves. The processor determines that the design space is high quality based on the PFIC and CMLI scores, and outputs a recommendation to proceed.