Abstract: A machine learning (ML) method for predicting an electronic structure of an atomic system. The method includes receiving an atomic identifier and an atomic position for atoms in the atomic system; receiving a basis set including rules for forming atomic orbitals of the atomic system; forming the atomic orbitals of the atomic system; and predicting an electronic structure of the atomic system based on the atom identifier, the atom position for the atoms in the atomic system, and the atomic orbitals of the atomic system. The ML method is capable of extremely accurate and fast molecular property prediction. The ML can directly purpose basis dependent information to predict molecular electronic structure. The ML method, which may be referred to as an orbital mixer model, uses multi-layer perception (MLP) mixer layers within a simple, intuitive, and scalable architecture to achieve competitive Hamiltonian and molecular orbital energy and coefficient prediction accuracies.

Abstract: Presented herein are predictive consultation techniques for use with medical devices. The techniques presented herein, sometimes referred to herein as “predictive medical device consultation techniques,” can include, for example, generation of one or more clinical predictions related to timing of future clinical appointments and/or one or more clinical predictions related to the selection of a medical device for the recipient.

Abstract: An information processing apparatus includes a first generation unit configured to generate a list of one or more disease names from an affected area image of a patient, a first determination unit configured to determine a name of a part having an affected area, an acquisition unit configured to acquire a previous medical examination record for the part having the affected area, a second determination unit configured to detect an excluded disease name or an examination result excluding a possibility of a specific disease described in a medical examination history and determine an or the excluded disease name, and a display unit configured to display a disease name or disease names in the list of the one or more disease names that are not described in a list of the excluded disease name, differently from the excluded disease name in the list of the excluded disease name.

Abstract: The present embodiments relate to a multimodal cryptographic bio-human machine interface (“CB-HMI”), which seamlessly translates the user's touch-based entries into encrypted biochemical, biophysical, and biometric indices. The CB-HMI features thin hydrogel-coated chemical sensors and inference algorithms to non-invasively and inconspicuously acquire biochemical indices such as circulating molecules that partition onto the skin (here, ethanol and acetaminophen). Additionally, the CB-HMI hosts physical sensors and associated algorithms to simultaneously acquire the user's heart rate, blood oxygen level, and fingerprint minutiae pattern. Additional or alternative embodiments include a touch-based non-invasive monitoring solution for lithium pharmacotherapy management. The system is constructed based on a thin organohydrogel-coated lithium ion-selective electrode (TOH-ISE), where the TOH coating was engineered to render stabilized conditions for sensing.

Abstract: A method for genome analysis is provided. The method includes receiving a nucleotide string comprising a plurality of nucleotides from at least a portion of one or more individual patients' genome. The method also includes identifying a plurality of variants in said nucleotide string, assigning each identified variant a score based on a location of a variant and a predicted functional consequence, and determining a strength of a variation responsible for a trait or phenotypic manifestation of the variants. The method also includes identifying at least one phenotype, and displaying, in a graphic unit interface of a client device, said nucleotide string, the identified variants, and the at least one phenotype, in one or more genetic elements for one or more individual patients. A system and a non-transitory, computer-readable medium storing instructions to perform the above method are also provided.

Abstract: The embodiments of the invention provide an intelligent shared cryogenic physical therapy system, including cryogenic physical therapy devices, human-machine interaction devices and a server. The server is configured to acquire target location information and recommend a cryogenic physical therapy device based on a relationship between the target location information and pre-recorded location information of each of the cryogenic physical therapy devices; and send a use request to a human-machine interaction device when a target cryogenic physical therapy device is selected and it is determined that the account balance meets a fee deduction condition. The human-machine interaction device can acquire the use request and generate the control instruction. A programmable controller of the cryogenic physical therapy device is configured to control the physical therapy module to perform an operation indicated by the control instruction when receiving the control instruction.

Abstract: A method and system for merging healthcare records across multiple locations is presented. The method first creates anonymized healthcare records by removing personally identifiable information. The method then converts each record into an embedding and appends a site locator identifying only the originator of the healthcare record. Then these embeddings are combined with similarly processed embeddings from multiple sites to create a merged database of embeddings derived from patient healthcare records. A classifier is trained to predict likely outcomes based on the merged database of embeddings. For a new patient, the corresponding healthcare record is converted to an embedding and the merged database of embeddings is then searched for a most similar patient and a treatment is recommended for the new patient, based on the prediction of the classifier.

Abstract: Object information is received via an application programming interface (API) from a requesting computing device. The object information is (a) extracted from a machine-readable code associated with the object, or (b) derived from information extracted from the machine-readable code associated with the object. A non-sequential parsing process is performed to the object information to identify one or more values for one or more fields of a plurality of unique fields. Performing the non-sequential parsing process includes applying a plurality of regular expressions to the object information to identify the one or more values. Each of the plurality of regular expressions is configured to identify values for at least one field of the plurality of unique fields. For each of the one or more values, a data object is that comprises the value and information indicative of the field for the value.

Abstract: An apparatus for configuring a wearable device for exercise tracking includes a data storage unit for storing sensor data generated by a sensor arrangement in the wearable device based on sensed movement of the wearable device and optical movement data including representations of an individual obtained from an image-based monitoring system; and a processing unit configured to: execute a movement tracker model on the sensor data to determine a first exercise activity and an associated first confidence indicator; execute an optical tracker model on the optical movement data to determine a second exercise activity and an associated second confidence indicator; process the movement tracker model based on the first confidence indicator and the second confidence indicator.

Abstract: A method of providing a preview version of a book over a computer network, the method comprising: apportioning the book into a plurality of content segments; modifying the book by rearranging at least a subset of the plurality of content segments to create a shuffled configuration of the book; initiating a preview session and displaying at least a first content segment from said shuffled configuration of the book in a preview window; displaying a next group of content segments from said shuffled configuration of the book during said preview session upon receiving a prompt from user to continue browsing; and controlling the availability of said shuffled configuration of the book during said preview session. A user may further customize preview version by providing a search input or by selecting a page range. Shuffled preview version may include one or more advertisements.

Abstract: Comprehensive patient-facing screening may provide diagnostics, real-time alerts, and feedback relating to a wide range of health and medical-related issues. The methods and systems for comprehensive patient-facing screening described provide feasible, user-friendly use, and may improve operations, processes, and connection to clinical care for users, such as veterans.

Abstract: A computing device can obtain usage data associated with the device. The usage data indicate how the computing device operates or how the device is used. The device can analyze the usage data to recognize usage patterns. The usage patterns can correspond to recurring actions or tasks initiated by the user using the device, such as actions or tasks initiated due to the user's habits and/or routines. Based on the usage patterns, the device can determine a task that has a sufficient likelihood of being performed using the device within a specified or determined time (e.g., 5 minutes from now, one year from now, etc.). The device can provide information (e.g., recommendations) associated with the task, and likely relevant to the user. The user can use the provided information to perform the task, thereby increasing the ease of access or efficiency associated with performing the task.

Abstract: Systems and methods described herein track bartering using distributed ledger techniques to, for example, facilitate the establishment of a bartering marketplace that enables users to barter for, and ultimately exchange, services and/or goods with each other. In certain embodiments, a monetary value may be assigned to each service and/or good to be bartered to establish appropriate bartering baselines. In addition, in certain embodiments, additional monetary value exchanges may be tracked for particular exchanges to make sure that the exchanges are fair.

Abstract: A device and method may determine whether a patient is projected to run out of a first prescription medication within a first window extending a first number of days ahead of a current day. A device may determine whether the patient is eligible to receive a refill of one or more second prescription medications within a second window extending a second number of days from a day when the patient is projected to run out of the first prescription medication. A device may send an electronic message to the patient with an option of a refill order of the first prescription medication and the one or more second prescription medications and receives a refill order of one or both of the first prescription and the one or more second prescriptions.

Abstract: An example computer-implemented method for providing diagnosis assistance includes receiving initial data associated with a diagnostic test result of a subject, selecting from among a plurality of machine-learning logic a machine-learning logic for execution based on a type of the diagnostic test result, determining by executing the machine-learning logic and based on the initial data a similarity between the initial data and diagnostic test result data stored in a database, based on the similarity between the initial data and the diagnostic test result data being within a similarity threshold providing an inquiry for display at the remote computing device to solicit additional information useful to resolve the undetermined outlier, receiving input data from the remote computing device in response to the inquiry, and storing the input data in the database.

Abstract: A method and system for generating a protein sequence is implemented using a computer-implemented neural network. An empty or partially filed sequence of node elements, representing amino acid positions of the protein sequence, and an edge index, having edge elements defining physical interaction between amino acid positions, are received. The computer-implemented neural network operates to determine enhanced edge attribute values for edge elements of the edge index and enhanced amino acid values for node elements of the sequence. Amino acid values are generated for elements of the partially filed sequence having missing values.

Abstract: In an aspect, a system for determining a liquid level in a drug delivery device is presented. The system includes a first spring and a second spring positioned adjacent the first spring. The system includes a rod configured to compress at least the first spring and contact the second spring. The system includes a sensing element in communication with the first spring and the second spring. The sensing element is configured to detect a difference in voltage of at least the first spring. A difference in voltage of at least the first spring corresponds to an amount of liquid drug of the drug delivery device.

Abstract: An artificial intelligence-based system comprises an input preparation module that accesses a sequence database and generates an input base sequence. The input base sequence comprises a target base sequence with target bases, wherein the target base sequence is flanked by a right base sequence with downstream context bases, and a left base sequence with upstream context bases. A sequence-to-sequence model processes the input base sequence and generates an alternative representation of the input base sequence. An output module processes the alternative representation of the input base sequence and produces at least one per-base output for each of the target bases in the target base sequence. The per-base output specifies, for a corresponding target base, signal levels of a plurality of epigenetic tracks.

Abstract: Techniques described herein are directed to determining that multimedia content displays a representation of an item offered for sale (1) at a first timestamp and (2) at a first location relative to a viewable window of a user device; generating an interactive element comprising an e-commerce tag interactable for purchase of the item; rendering, at the first timestamp, the interactive element on a first portion of the multimedia content and positioned relative to the representation of the item in a predetermined spatial configuration in the viewable window; rendering, at a second timestamp, the interactive element on a second portion of the multimedia content and positioned relative to the representation in the same spatial configuration; detecting an interaction with the interactive element; and based on detecting the interaction, displaying a graphical user interface configured to allow the user to purchase the item.

Abstract: The disclosure relates to analysing genetic data. In one arrangement, a method operates on input data comprising strengths of association between one or more phenotypes including a target phenotype and a plurality of genetic variants. A fine-mapping algorithm is applied to all or a subset of the input data to identify one or more independent phenotype-variant associations. A set of one or more fine-mapped variants is identified for each association. A fine-mapping predictive model is calculated on the basis of the input data and the set of fine-mapped variants. The effect on the target phenotype of the set of fine-mapped variants is subtracted from the input data to obtain residual association data. A machine learning algorithm is applied to the residual association data to identify further predictive correlations between the target phenotype and the plurality of genetic variants.