Abstract: Systems and methods are provided for integrating artificial intelligence (AI) workflows. In one example, a method includes receiving, from a medical image storage device, an instance availability notification, in response to determining that the notification indicates that one or more medical images have been saved at the medical image storage device, querying the medical image storage device to retrieve metadata associated with the one or more medical images, initiating a work-item with an AI orchestration platform for the metadata, and receiving, from the AI orchestration platform via the work-item, AI results related to the one or more medical images.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting future patient health using neural networks. One of the methods includes receiving electronic health record data for a patient; generating a respective observation embedding for each of the observations, comprising, for each clinical note: processing the sequence of tokens in the clinical note using a clinical note embedding LSTM to generate a respective token embedding for each of the tokens; and generating the observation embedding for the clinical note from the token embeddings; generating an embedded representation, comprising, for each time window: combining the observation embeddings of observations occurring during the time window to generate a patient record embedding; and processing the embedded representation of the electronic health record data using a prediction recurrent neural network to generate a neural network output that characterizes a future health status of the patient.

Abstract: A delivery device includes a circuit for receiving an authentication signal. The delivery device contains a substance encapsulated therein. The delivery device determines whether a user is authenticated based upon the authentication signal and an identifier stored within the delivery device. The delivery device heats, responsive to determining that the user is not authenticated within a predetermined time period after the delivery device being ingested by the user, the substance encapsulated within the delivery device.

Abstract: A computer-implemented method can include acquiring data from at least one data source, the acquired data including health data for a patient. The acquired data can be transformed into episode model data according to a context-specific data model and the episode model data can be stored in a database. The method also includes generating at least one inverted index document for at least a portion of an episode for the patient based on the episode model data.

Abstract: In accordance with the principles of the invention, methods, systems, and computer-readable mediums are provided for positioning cellular analysis data including measuring a similarity between pixel data in a target sample data and pixel data in a template data. An offset position is determined based on the measured similarity. The pixel data in the template data is shifted based on the offset position to produce shifted template data having pixel data at shifted locations which match the corresponding pixel data in the target sample data.

Abstract: A computerized method and system for generation an immunization schedule for a person in healthcare environment is provided. The system receives a request for an immunization schedule for a person and obtains information from an electronic medical record of the person stored within a comprehensive healthcare system. The system obtains one or more immunization schedules and utilizes the information from the electronic medical record of the person and the immunization schedule to generate a customized immunization schedule for the person. In another embodiment, the system receives immunization information for a person and stores the immunization information in the electronic medical record of the person within a comprehensive healthcare system.

Abstract: A pharmacy benefits management system and method. A processor server has claim information relating to pharmacy benefits claims, and information relating to a claims processing formularly stored therein. A provider server has pharmacy benefits plan structure information stored therein. A management server has price information relating drugs in various classes and a processing module for correlating the claim information with the benefits plan structure information and the formularly information to identify drugs dispensed to patients, expenses associated with the drugs in accordance with the pharmacy benefits plan structure information, alternative drugs in the same class as the drugs and expenses associated with the alternative drugs.

Abstract: A method for managing health plans includes the use of theoretically derived mathematical models. The methods may be used in the analysis of health insurance products. The method may also assist in the selection of a particular health plan's benefit and contribution strategy. The analysis may further be used in the selection of a health plan's funding arrangement.

Abstract: A method for remote medical consulting includes collecting diagnostic data using at least one wearable device contoured to at least a portion of a person's hand, transmitting the diagnostic data to a remote location, transmitting audio data and video images of the patient to the remote location, and communicating diagnosis and/or treatment information to the patient based at least in part on the diagnostic data. The treatment information may include a prescription electronically transmitted to the patient or a pharmacy. The method includes billing of the patient via credit or debit card, bank account, or a third party, such as an insurance company. The diagnostic data as well as the audio and video data may be transmitted wirelessly via cellular or satellite communication networks and/or using a wide area computer network such as the internet.

Abstract: An outlier detector that exploits the existing risk structure of the decision problem in order to discover risk assignments that are globally inconsistent is described. The technique works on a set of candidates for which risk categories have already been assigned. In the case of insurance underwriting, the invention pertains to the premium class assigned to an application. For this set of labeled candidates, the system finds all such pairs of applications belonging to different risk categories, which violate the principle of dominance. The invention matches the risk ordering of the applications with the ordering imposed by dominance and uses any mismatch during the process to identify applications that were potentially assigned incorrect risk categories.

Abstract: Methods and systems are provided for assigning liability estimates to past or theoretical accidents. Embodiments may be used in association with methods and systems for estimating liability in a vehicle accident. In one embodiment, liability estimation in a vehicle accident may be based on a plurality of characteristics that describe the accident. The characteristics from an actual accident may be compared to those in a past or theoretical accident. Liability may be estimated from the assigned liability associated with a nearest matching past or theoretical accident.

Abstract: Methods and systems are provided for estimating liability in an accident. In one embodiment, liability estimation in a vehicle accident may be based on a plurality of characteristics that describe the accident. These characteristics may include: the configuration of the roadway, the type of accident, right of way, and impact points of each vehicle. In an embodiment, impact points may be grouped into impact groups. A base liability may be assigned to each impact group. The characteristics from an actual accident may be compared to those in a past or theoretical accident. Liability may be estimated from a preassigned liability associated with a nearest matching past or theoretical accident. The liability estimate may include a base liability and one or more adjustments due to various factors.

Abstract: Methods and systems are provided for determining inconsistencies between two or more sets of characteristics relating to an accident. In an embodiment, sets of characteristics relating to an accident may be used to determine liability in the accident. The at least one of the sets of characteristics may be determined from witness statements. The at least one set of characteristics determined from witness statements may be compare to other sets of characteristics determined from witness statements or to other sets of characteristics determined in other ways. The comparison may determine if there are inconsistencies in the sets of characteristics.

Abstract: Methods and systems are provided for estimating right of way in an accident. In one embodiment, right of way estimation in a vehicle accident may be based on a plurality of characteristics that describe the accident. The characteristics from an actual accident may be compared to those in a past or theoretical accident.

Abstract: A method for dispensing medical items designated in a prescription, such as an electronic prescription, including providing the electronic prescription to a server, and the server providing the electronic prescription to a pharmacy or other agent that fills the prescription and provides the medical items to the patient. A consent statement is provided by the patient for permission to the pharmacy to receive and fill the prescription and for permission to the server to receive and forward the prescription. Secure communications are provided for key communications to establish trust of identity of the parties and entities.

Abstract: A healthcare risk index is generated using a patient or individual's pharmacy claims. The index may be used to explain and predict variation in pharmacy-related costs and variation in total healthcare costs or utilization. In particular, the index is generated by first examining the individual's pharmacy claims to identify any chronic conditions possessed by the individual. Similarly, the individual's pharmacy claims are examined to identify any compliance medications prescribed to the individual. The chronic condition information is used to generate a chronic condition score by summing regression coefficients for each chronic condition possessed by the individual. Likewise, the compliance medication information is used to generate a compliance medication score by summing products of regression coefficients for each compliance medication prescribed to the individual with associated medication supply weights.

Abstract: The invention relates to a method and system of physician economic performance evaluation in which the relative medical difficulty associated with patients admitted by a particular physician is determined and, given that measurement, judgments made concerning the relative amount of inpatient resources that the physician required. Also, one application of the present invention relates to a method for gainsharing of physician services using a surplus allocation methodology for rewarding physicians in relation to their performance. An incentive pool is determined from previous patient claims and payments made to physicians in advance, such as in a base year. Best practice norms are established for a plurality of classified diagnosis groups. In one embodiment of the present invention, the classified diagnosis related groups are adjusted for severity of illness to compensate for actual clinical challenges faced by individual physicians.

Abstract: The present invention discloses methods for conveniently providing a complete medication profile of a patient. A medication profile report may be obtained on-line by the patient or a registered provider. In addition to information regarding the expiration of prescriptions, the patient's compliance with the prescriber's directions for usage, and the names of medications being used by a patient, the medication profile report also provides the therapeutic classes of each medication, possible drug-drug interactions, and possible side effects. Convenient access to such complete medication information is highly desirable to the patient and his or her provider.

Abstract: A system and method for matching patients with clinical trials and particular trial sites, prequalifying patients for clinical trials and trial sites, and providing information to patients to allow them to inform themselves about available clinical trials and trial sites. The method comprises receiving patient profile information for a patient at a server connected to a computer network, the patient profile information submitted by a user at a terminal connected to the network, comparing the patient profile information with acceptance criteria for clinical trials stored in a database, the comparison performed by the server, determining whether the patient prequalifies for any of the clinical trials, and notifying the user and the trial site whether the patient has prequalified for any clinical trials.

Abstract: A method provides for inputting and storing data for a clinical study in a uniform manner by different study locations. Accordingly, the method comprises generation of an input platform program for an input of data of a clinical study, distribution of the input platform to input locations, calling up and activating the input platform program dependent on a participant characteristic linked with a study participant in the clinical study, inputting the data at an input location via an input platform generated by the input platform program, and storing the input data.